Open-weight models, attested on your hardware.
Every score on this page came from a local Ollama daemon, Q4_K_M quants on a consumer GPU, running the same canonical sample sets as the cloud-API attestations. Each result is Ed25519-signed by the publisher's local attestor and replayable in your browser.
Local runs
0
Ed25519 signed
Models
0
open-weight, quantized
Benchmarks
0
deterministic graders
Perfect runs
0
100% scores
Local model leaderboard
Average score across each model's set of attested benchmark runs. Sorted by mean accuracy. n < 30 runs excluded from the per-(model, bench) matrix below.
| # | Model | Runs | Avg score | Benches | Perfect |
|---|---|---|---|---|---|
| No local runs yet. Post the first attested local score → | |||||
Top (model × benchmark) cells
Best attested run per (model, benchmark) pair. Click any cell to replay the signature in-browser.
Matrix populating…
Run your own local benchmark
Pull a model in Ollama, run our open runner, get a signed receipt your community can re-verify.
Local runner docs →